Modeling the Chlorophyll-a from Sea Surface Reflectance in West Africa by Deep Learning Methods: A Comparison of Multiple Algorithms

TL;DR

This study compares eight deep learning algorithms to accurately estimate chlorophyll-a concentrations from satellite sea surface reflectance data across multiple sensors in West Africa, demonstrating low error rates.

Contribution

It introduces a multi-sensor deep learning model that fuses satellite data to reliably predict chlorophyll-a, accounting for water and instrument biases.

Findings

Low mean absolute error between 0.07 and 0.13 mg/m3

Effective multi-sensor data fusion improves prediction accuracy

Best model outperforms traditional methods in estimating chlorophyll-a

Abstract

Deep learning provide successful applications in many fields. Recently, machines learning are involved for oceans remote sensing applications. In this study, we use and compare about eight (8) deep learning estimators for retrieval of a mainly pigment of phytoplankton. Depending on the water case and the multiple instruments simultaneouslyobserving the earth on a variety of platforms, several algorithm are used to estimate the chlolophyll-a from marine reflectance. By using a long-term multi-sensor time-series of satellite ocean-colour data, as MODIS, SeaWifs, VIIRS, MERIS, etc, we make a unique deep network model able to establish a relationship between sea surface reflectance and chlorophyll-a from any measurement satellite sensor over West Africa. These data fusion take into account the bias between case water and instruments. We construct several chlorophyll-a concentration prediction deep learning based models, compare them and therefore use the best for our study. Results obtained for accuracy training and test are quite good. The mean absolute error are very low and vary between 0,07 to 0,13 mg/m3.